Does the 10B model accept navigation/route inputs?
Does the 10B model accept navigation/route inputs?
Does the model produce meta-actions or support general VQA?
Does the model produce meta-actions or support general VQA?
While we have experimented with meta-action and general VQA capabilities, the released model does not include these features. Alpamayo 1 is designed specifically for trajectory prediction with Chain-of-Causation reasoning, producing trajectory + reasoning trace outputs.
Was the 10B model post-trained with Reinforcement Learning (RL)?
Was the 10B model post-trained with Reinforcement Learning (RL)?
No. The current 10B model release has not undergone RL post-training. While the paper describes RL stages for improving reasoning quality and action consistency, this release focuses on the supervised learning components. As mentioned above, we may release RL post-trained models in future releases.
What are the minimum GPU requirements?
What are the minimum GPU requirements?
You need an NVIDIA GPU with at least 24 GB VRAM for inference. Tested configurations include RTX 3090, A100, and H100. Running on GPUs with less memory (e.g., 16 GB) will likely result in CUDA out-of-memory errors.
Can I use this model in production / commercial applications?
Can I use this model in production / commercial applications?
No. The model weights are released under a non-commercial license. This release is intended for research, experimentation, and evaluation purposes only. See the License page and the HuggingFace Model Card for details.